DAL poses batch active learning as a binary classification task between labeled and unlabeled data to select informative examples for labeling.
Deep Bayesian Active Learning with Image Data
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Even though active learning forms an important pillar of machine learning, deep learning tools are not prevalent within it. Deep learning poses several difficulties when used in an active learning setting. First, active learning (AL) methods generally rely on being able to learn and update models from small amounts of data. Recent advances in deep learning, on the other hand, are notorious for their dependence on large amounts of data. Second, many AL acquisition functions rely on model uncertainty, yet deep learning methods rarely represent such model uncertainty. In this paper we combine recent advances in Bayesian deep learning into the active learning framework in a practical way. We develop an active learning framework for high dimensional data, a task which has been extremely challenging so far, with very sparse existing literature. Taking advantage of specialised models such as Bayesian convolutional neural networks, we demonstrate our active learning techniques with image data, obtaining a significant improvement on existing active learning approaches. We demonstrate this on both the MNIST dataset, as well as for skin cancer diagnosis from lesion images (ISIC2016 task).
verdicts
UNVERDICTED 5representative citing papers
SCAS selects verified teacher answers using a forward-only proxy for student learning cost derived from token-wise gradients, improving student performance over strongest-teacher selection across 30 teachers, 6 students, and 6 tasks.
A cognitive-uncertainty guided two-stage KD framework filters to 10.3% of samples to reach 0.9585 MAP@3 and 84.38% accuracy with a 4B model, beating larger LLMs on misconception classification.
Informativeness and diversity of samples selected by active learning show no correlation with test performance on translation tasks using few samples; ordering and pre-training effects dominate instead.
A hybrid approach applies active learning at edge devices and federated learning at fog nodes to reduce training data volume and communication cost for image classification in distributed edge-fog setups.
citing papers explorer
-
Discriminative Active Learning
DAL poses batch active learning as a binary classification task between labeled and unlabeled data to select informative examples for labeling.
-
The Strongest Teacher Is Not Always the Best Teacher: Student-Centric Answer Selection
SCAS selects verified teacher answers using a forward-only proxy for student learning cost derived from token-wise gradients, improving student performance over strongest-teacher selection across 30 teachers, 6 students, and 6 tasks.
-
Cognitive-Uncertainty Guided Knowledge Distillation for Accurate Classification of Student Misconceptions
A cognitive-uncertainty guided two-stage KD framework filters to 10.3% of samples to reach 0.9585 MAP@3 and 84.38% accuracy with a 4B model, beating larger LLMs on misconception classification.
-
Testing the Assumptions of Active Learning for Translation Tasks with Few Samples
Informativeness and diversity of samples selected by active learning show no correlation with test performance on translation tasks using few samples; ordering and pre-training effects dominate instead.
-
Active Learning Solution on Distributed Edge Computing
A hybrid approach applies active learning at edge devices and federated learning at fog nodes to reduce training data volume and communication cost for image classification in distributed edge-fog setups.